We present a general machine learning framework for modelling the phenomenon of missing information in data. We propose a masking process model to capture the stochastic nature of...
We give a new model of learning motivated by smoothed analysis (Spielman and Teng, 2001). In this model, we analyze two new algorithms, for PAC-learning DNFs and agnostically learn...
Adam Tauman Kalai, Alex Samorodnitsky, Shang-Hua T...
We address well-studied problems concerning the learnability of parities and halfspaces in the presence of classification noise. Learning of parities under the uniform distributi...
The Kushilevitz-Mansour (KM) algorithm is an algorithm that finds all the “large” Fourier coefficients of a Boolean function. It is the main tool for learning decision trees ...
We consider the parallels between the preference elicitation problem in combinatorial auctions and the problem of learning an unknown function from learning theory. We show that l...